© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 13626
    Prev
    Next
    INDEX
    Explanations

    references to specific names or terms associated with the letter 'J'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Token "J" followed by other characters

    np_acts-logits-general · gemini-2.0-flash

    j followed by specific tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    帖最后由
    -0.58
     nødvendig
    -0.54
     cheminée
    -0.53
     måte
    -0.52
     operativos
    -0.51
     række
    -0.51
     aceptas
    -0.50
    jší
    -0.50
    köy
    -0.49
     corrector
    -0.49
    POSITIVE LOGITS
     autorytatywna
    0.80
     صوتيه
    0.72
     Jamb
    0.71
     GenerationType
    0.65
    SPJ
    0.61
    bootstrapcdn
    0.60
     Jop
    0.60
    หวัด
    0.59
     initComponents
    0.59
    zeera
    0.59
    Activations Density 0.607%

    No Known Activations